Atlas · Name Abogados

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), yet the description adds meaningful behavior: search runs over the metadata 'ficha' (título, referencia, epígrafe, descriptores, resumen...) rather than full text, and that ficha was generated by automated tools, a quality caveat the annotations do not convey. It also discloses that each result carries the link to the official document. No auth, rate-limit, or pagination caveats are given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense, well-organized paragraph that front-loads the core purpose before layering scope, accepted query forms, and the ficha caveat. It is on the long side and repeats the notion of reading/citing the official document, but nearly every sentence adds information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, no-output-schema tool with annotations in place, the description supplies the missing return-value context (each result links to the official document) and clarifies that matching is against metadata, not document text. Only minor gaps remain, such as pagination limits already documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 89% schema coverage the baseline is 3, but the description genuinely enriches the q parameter by enumerating accepted input shapes — thematic phrases, references like «C-1237 de 2025» placed first, and norm numbers like «2.2.1.1.2.2.4» — which goes beyond the schema's terse 'Texto libre'. The remaining filters (tipo, fechas, orden, autoridad, descriptor) are left to the schema, which already documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (busca por relevancia) and a precisely scoped resource (Atlas, el archivo de documentos oficiales de derecho público colombiano), even naming the institutions behind it. It also delineates its role as FILTRAR frente a la lectura/cita del documento oficial, which separates it from the sibling atlas_obtener without naming it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames the use case: 'Sirve para FILTRAR: decidir qué documentos leer', and points to the official link as the thing to read and cite. It gives clear context for when to reach for it, though it never names atlas_obtener as the alternative for actually retrieving the document, leaving that inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the description only needs to add context beyond that. It does: it discloses that summaries are Atlas-generated rather than source text, and that the full document text is not returned but lives behind the official link. Those are genuinely useful behavioral facts an agent cannot derive from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single well-formed sentence, front-loaded with the core purpose and then enumerating contents. Nothing is padded, though the long comma-list of returned fields makes it dense; it could be broken into two sentences for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing the return payload, and it does so thoroughly by listing every field of the record. It also notes that the full text must be reached via the official link. Only the empty/no-match and disambiguation behavior is left implicit (partially covered by the schema's candidate note).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are fully documented in the schema, including the important 'sin año, devuelve los candidatos' fallback. The description echoes the reference and slug examples but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete action and resource: it returns the complete record ('la ficha completa') for a document, reachable either by reference or by slug. The enumeration of the record's contents (epígrafe, problema jurídico, resumen, citas, descriptores, relacionados, enlace oficial) makes the output scope very concrete. It never contrasts itself with the sibling atlas_buscar, so the agent must infer the lookup-vs-search distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent the two accepted lookup keys ('por referencia ... o por slug'), which implicitly frames this as a direct-identifier fetch rather than a search. However, it never explicitly says when to use this instead of atlas_buscar, nor any prerequisite such as requiring an exact reference or slug. Usage is implied rather than prescribed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.